Create an AI Guardrails Data Classification

You can create an AI guardrails data classification to help you monitor content with specific characteristics in AI application prompts and responses. Custom AI guardrails data classifications must be used in AI guardrails rules.

The building blocks for AI guardrails data classifications are AI guardrails data identifiers. The data identifiers that you choose for a data classification determine the type of data for which rules using that data classification will scan. Secure Access provides a set of built-in AI guardrails data identifiers you can use to create your custom AI guardrails data classifications.

To delete or edit an AI guardrails data classification, see Delete or Edit an AI Guardrails Classification.

Prerequisites

Full Admin user role. For more information, see Manage Accounts.

Procedure

Navigate to Secure > Settings > Data Classification > AI Guardrails Classifications and click Add.

Give your AI guardrails classification a meaningful name and description.
Under Include Data Identifiers, select a Boolean operator to separate the identifiers included in the classification.

OR—At least one of the data identifiers included must match during rule evaluation.

AND—All of the data identifiers included must match during rule evaluation.

Under Include Data Identifiers, expand Built-in Data Identifiers and select data identifiers to include in the AI guardrails classification. Use the search box to quickly find a particular identifier you have in mind. To see the description for an identifier, click the arrow to the right of its name.

Click Save.

Your new classification is listed on the Data Classification page under AI Guardrails Classifications, and will be available to you when you add an AI guardrails rule to the DLP policy.

Manage AI Guardrails Data Classifications < Create an AI Guardrails Data Classification > Copy and Customize a Built-In AI Guardrails Data Classification